state: generation 11924 (cycle)

This commit is contained in:
2026-09-21 23:49:44 +00:00
parent c31ab7906f
commit df7a46930d
10 changed files with 2158 additions and 2090 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T23:47:10.105504+00:00",
"lastSyncTime": "2026-09-21T23:47:09.753992+00:00",
"generatedAt": "2026-09-21T23:49:31.238696+00:00",
"lastSyncTime": "2026-09-21T23:49:30.866198+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3206,7 +3206,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 204,
"failureBreakdown": {
"ambiguous_runtime": 109,
"ambiguous_runtime": 110,
"context_length": 1,
"framework_architecture_unsupported": 155,
"memory_capacity": 10,
@@ -3214,7 +3214,7 @@
"repository_structure": 27,
"tokenizer_compatibility": 11
},
"failureCount": 314,
"failureCount": 315,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -3224,8 +3224,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 314,
"unresolvedFailureCount": 109
"total": 315,
"unresolvedFailureCount": 110
},
"Biren_166m|unknown|feature_emb": {
"attributableFailureCount": 0,
@@ -3526,12 +3526,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 4,
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 21,
"failureCount": 22,
"failureRate": 1.0,
"framework": "vllm-customized",
"pendingCount": 0,
@@ -3541,8 +3541,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 21,
"unresolvedFailureCount": 15
"total": 22,
"unresolvedFailureCount": 16
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 13,
@@ -5532,7 +5532,7 @@
"decisionSuccessRate": 0.0242,
"decisionTotal": 3635,
"failureBreakdown": {
"ambiguous_runtime": 1499,
"ambiguous_runtime": 1500,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5546,15 +5546,15 @@
"tokenizer_compatibility": 412,
"参数/模板问题": 46
},
"failureCount": 5957,
"failureCount": 5958,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6045,
"unresolvedFailureCount": 1545
"total": 6046,
"unresolvedFailureCount": 1546
},
"vllm-customized": {
"attributableFailureCount": 6,
@@ -5562,20 +5562,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 4,
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 21,
"failureCount": 22,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 21,
"unresolvedFailureCount": 15
"total": 22,
"unresolvedFailureCount": 16
},
"vllm-mlu": {
"attributableFailureCount": 21,
@@ -5700,7 +5700,7 @@
"unresolvedFailureCount": 121
}
},
"generatedAt": "2026-09-21T23:47:10.094226+00:00",
"generatedAt": "2026-09-21T23:49:31.228042+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5734,7 +5734,7 @@
"decisionSuccessRate": 0.1636,
"decisionTotal": 385,
"failureBreakdown": {
"ambiguous_runtime": 183,
"ambiguous_runtime": 184,
"context_length": 1,
"framework_architecture_unsupported": 178,
"memory_capacity": 19,
@@ -5746,15 +5746,15 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 964,
"failureCount": 965,
"failureRate": 0.9387,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 63,
"successRate": 0.0613,
"total": 1027,
"unresolvedFailureCount": 640
"total": 1028,
"unresolvedFailureCount": 641
},
"Biren_166m": {
"attributableFailureCount": 186,
@@ -5821,7 +5821,7 @@
"decisionSuccessRate": 0.209,
"decisionTotal": 67,
"failureBreakdown": {
"ambiguous_runtime": 111,
"ambiguous_runtime": 112,
"framework_architecture_unsupported": 44,
"memory_capacity": 4,
"model_load": 3,
@@ -5829,15 +5829,15 @@
"参数/模板问题": 34,
"验证失败": 22
},
"failureCount": 220,
"failureRate": 0.9402,
"failureCount": 221,
"failureRate": 0.9404,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.0598,
"total": 234,
"unresolvedFailureCount": 167
"successRate": 0.0596,
"total": 235,
"unresolvedFailureCount": 168
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -7956,9 +7956,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
@@ -7970,8 +7970,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Ascend_910-b4|vllm|text-generation|llama|none": {
"attributableFailureCount": 1,
@@ -9883,6 +9883,29 @@
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -18058,15 +18081,15 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 9,
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 14,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T19:49:37.657075+00:00",
"lastTerminalAt": "2026-09-21T23:49:30.866184+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -18074,8 +18097,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 12
"total": 15,
"unresolvedFailureCount": 13
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 0,
@@ -19505,6 +19528,31 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-21T23:49:30.866184+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -19787,9 +19835,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 5
},
"failureCount": 6,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T17:22:47.256939+00:00",
@@ -19802,8 +19850,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 5,
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x8|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
@@ -24485,9 +24533,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
@@ -24500,8 +24548,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Ascend_910-b4|vllm|text-generation|llama|awq|33": {
"attributableFailureCount": 0,
@@ -27229,6 +27277,30 @@
"total": 3,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|none|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -38621,15 +38693,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16441,
"totalRecords": 16635,
"terminalRecords": 16443,
"totalRecords": 16637,
"totals": {
"attributableFailureCount": 5925,
"decisionFailureRate": 0.8619,
"decisionSuccessRate": 0.1381,
"decisionTotal": 6874,
"failureBreakdown": {
"ambiguous_runtime": 4054,
"ambiguous_runtime": 4056,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 105,
@@ -38645,31 +38717,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15492,
"failureCount": 15494,
"failureRate": 0.9423,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 949,
"successRate": 0.0577,
"total": 16441,
"unresolvedFailureCount": 8642
"total": 16443,
"unresolvedFailureCount": 8644
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -38709,6 +38781,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16635,
"summarizedRecords": 16637,
"version": 1
}